Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    breaking down into components

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    necessarily
    0.87
     thereby
    0.84
     conceivably
    0.78
     polyvinyl
    0.74
     lesquels
    0.73
    Dragging
    0.71
     Alkal
    0.70
    presumably
    0.69
     Resp
    0.69
     Presumably
    0.69
    POSITIVE LOGITS
     combining
    1.30
     involving
    1.18
     containing
    1.13
     featuring
    1.11
     consisting
    1.05
     considering
    0.90
     being
    0.90
     comprising
    0.88
     encompassing
    0.88
     incorporating
    0.87
    Act Density 0.198%

    No Known Activations